Fujitsu Laboratories Ltd. announces the development of a facial recognition technology that uses conventional cameras to successfully identify efforts to spoof authentication systems. This includes impersonation attempts in which a person presents a printed photograph or an image from the internet to a camera.

Conventional technologies rely on expensive, dedicated devices like near-infrared cameras to identify telltale signs of forgery, or the user is required to move their face from side to side, which remains difficult to duplicate with a forgery. This leads to increased costs, however, and the need for additional user interaction slows the authentication process.

Convenience of face authentication

To tackle these challenges, Fujitsu has developed a forgery feature extraction technology that detects the subtle differences between an authentic image and a forgery, as well as a forgery judgment technology that accounts for variations in appearance due to the capture environment.

Fujitsu's new technology ultimately makes it possible to prevent impersonation with forgeries using only face images taken at the time of authentication, enhancing security without sacrificing the convenience of face authentication and contributing to the DX (digital transformation) of operations with improved personal authentication technologies.

Other authentication methods

It has proven difficult to determine the authenticity of a face by relying on a facial image alone

While biometric authentication continues to grow in popularity, many risks remain. In some cases, when facial images are disclosed on the Internet via SNS, etc., the possibility emerges that the image may become the target of malicious users if stolen due to the loss of an ID card with a facial photograph, etc.--because of the prevalence of such images, this makes facial authentication more vulnerable than other authentication methods, such as fingerprints or palm veins.

Smartphone screens, ID cards, and face images printed on paper vary in their appearance due to factors like reflections or blurring on a smartphone screen. It has proven difficult to determine the authenticity of a face by relying on a facial image alone because of the effects of similar fluctuations, such as reflections caused by fluorescent lights or sunlight, or blurring caused by facial movement.

General-purpose cameras

For this reason, special cameras like near-infrared cameras or depth cameras that measure the distance between the subject and the camera are used to catch typical signs of forgery. These methods remain imperfect, however, and lead to issues including increased costs for dedicated cameras and reduced convenience due to the addition of motion information required when using general-purpose cameras.

The development of technologies that can conveniently and inexpensively detect spoofing with general-purpose cameras has become a topic of consideration. Fujitsu has developed a technology that can detect the impersonation of others through photographs, etc. from face images taken with a general-purpose camera. The features of the developed technology are as follows.

Forgery feature extraction

Image processing technology is used to digitise the characteristic features of forgery

Various features characteristic of a forgery remains in images obtained by presenting the forgery to the camera, such as reflections on the terminal screen of a smartphone, and distortion of the shape of the face caused by taking a planar forgery. Fujitsu has developed a forgery feature extraction technique to express the difference between the forgery's characteristic features and the real face as determinable values.

First, the face image captured by the camera is separated into various elements that exhibit the characteristic features of forgery, such as reflection elements and shape elements. Next, image processing technology is used to digitise the characteristic features of forgery for each of the separated elements, and the characteristics of each element are combined to generate a characteristic for judgment. This makes it possible to identify counterfeits without information based on user operations.

Deep learning techniques

In the past, in order to respond to variations in image appearance caused by the capture environment, a single determination model was generated by training a system with face images containing various variations using machine learning. However, the wide range of variations in the way images are taken, depending on the type of forgery, such as a smartphone screen or ID card, complicates the boundary between the real face and the forgery, making it difficult to identify the forgery even with the latest Deep Learning techniques.

Therefore, Fujitsu has developed a technology that can correctly identify counterfeits by generating determination models that reduce the influence of variations by learning the categories of face images that have similar variations, such as face images taken at the office or face images taken by a window.

Counterfeit with machine learning

The development technology steps are divided into a training phase and a judgment phase. In the training phase, face images acquired in various environments are classified into categories such as window, backlight, and normally based on the capture environment, such as the intensity of light and the direction of light.

Next, a judgment model is made for determining whether the target is a real face or a counterfeit with machine learning, using the decision features generated by the forgery feature extraction technology for each category.

Inexpensive spoofing detection

The similarity between the input image and each category is calculated dynamically

In the judgment phase, in order to estimate which of the categories defined in the training phase the input image capture environment is close to, the similarity between the input image and each category is calculated dynamically. Next, in order to emphasise the result of the determination model of the category in which the input image and the environment are close to each other, a value obtained by multiplying the score indicating the authenticity output from each determination model by the weight based on the similarity with each category is used to determine whether or not the object is a fake.

By using these technologies, it becomes possible to identify counterfeits using only the information of face images taken by a general-purpose camera and to realise relatively convenient and inexpensive spoofing detection.

Personal authentication technology

Fujitsu reviewed its own evaluation data set collected in a general office environment or an environment where telework outside the office is assumed and confirmed that spoofing attempts can be detected with the same level of accuracy as before, even when there is no specified movement by a dedicated camera or a user. This makes it possible to prevent unauthorised access at a low cost without sacrificing convenience.

The technology offers the potential to improve security for workers remotely accessing company systems from offsite and to contribute to the digital transformation of operations through the advancement of enhanced personal authentication technology. Fujitsu aims to further improve the accuracy of its forgery detection technology with the aim of putting it into practical use by the end of the fiscal 2020 in March 2021.

Share with LinkedIn Share with Twitter Share with Facebook Share with Facebook
Download PDF version Download PDF version

In case you missed it

What are the new trends and opportunities in video storage?
What are the new trends and opportunities in video storage?

Video storage has been a challenge since the days of VCRs and videotape. Storing images is a central need for any video systems, especially one that is focused on the forensic and investigative aspects of video. Today, digital video is stored on hard drives and even in the cloud. Increasingly, video is considered “data” that drives a variety of video analytics and even artificial intelligence (AI) applications. We asked this week’s Expert Panel Roundtable: What are the new trends and opportunities in video storage?

How to deter thieves on construction sites
How to deter thieves on construction sites

Construction site theft can cause project delays, property damage and loss of profit for companies in the construction sector. It is imperative to deter thieves from targeting construction sites with the help of construction site security. Here, we look into the various security options and how they can help protect your firm from the threat of a break-in. Construction theft has soared during the COVID-19 Pandemic Construction site theft is an ever-increasing problem in the UK, costing the industry an estimated £800 million per year. Unfortunately, this type of crime has accelerated further throughout lockdown by an estimated 50% due to the abandonment of construction sites across the UK. With many uncertainties around a potential second wave in the UK, it is time for construction firms to enhance their security strategies to help prevent thieves from becoming opportunists on construction sites. Why are construction sites ‘easy’ targets? Construction sites can easily be targeted, as they typically lack adequate security loss prevention practices. The most popular security-related issues that are leading causes of construction site theft are: Poor overall site security Multiple pieces of equipment sharing the same keys Easy access to open cabs Unsecured sites, particularly at night and over weekends Lack of product identification systems If you do not want your site becoming a costly statistic, you might want to try implementing some or all of these preventive measures. Strengthen your perimeter Putting a clear boundary around a construction site will help to prevent youths and members of the public from inadvertently wandering onto the site. To stop opportunist thieves in their tracks, you will need to go one step further by erecting robust fencing and concrete blocks along with signage warning intruders about the consequences of trespassing. Putting a clear boundary around a construction site will help to prevent youths and members of the public from inadvertently wandering onto the siteIf potential trespassers can see that it would be too challenging to attempt a break-in, then they will look elsewhere to find another construction site which is not as well secured. Lock away valuable tools When considering the vulnerabilities in your construction site, it pays to think about this from the perspective of a criminal. What is it exactly that they are looking for? What can a thief steal easily to make money if they were to remove something from your site? Unfortunately, many construction firms do not lock away their tools, materials or vehicles properly, which makes them an easy target. Ensure valuable tools and materials are locked away and are not left unsecured or lying around. Criminals are mostly interested in scaffolding, bowsers and other valuables that are quick to sell on, so it is important to have a strategy in place to keep these locked away, safe and securely. Put tracking devices in your equipment If you are unable to securely lock away valuable tools, then modern technology makes securing equipment easier than ever before. Tracking devices can be installed onto vehicles and equipment; if any thief is unwise enough to steal from the site, site owners will be able to provide the location to the police who will be able to follow this up. Site owners should also engrave company identification numbers on valuable tools, equipment and vehicles so that it can easily be identified and will serve as proof who it rightly belongs to. Invest in CCTV Closed Circuit Television, otherwise known as CCTV, is renowned for being one of the most effective deterrents for thieves, especially when it comes to construction and building sites.The items that criminals steal from sites are notoriously hard to trace The items that criminals steal from sites are notoriously hard to trace, but if you have CCTV, there is a chance that you can capture clear footage to help bring criminals to justice, such as footage of the vehicle used and the car licence plate. CCTV cameras can help to oversee every inch of a construction site, and can even be hidden out of sight where required. Step up with regular site patrols With a wide range of security monitoring methods available, stepping up on regular site patrols can help to keep track and respond to any criminal activity taking place on your site. Traditional site patrols can be carried out on a schedule by professional SIA-approved security agents. With the presence of guards patrolling a construction site, any criminals in the area will be deterred to force entry onto the site. Schedule supply deliveries on an as-needed basis To prevent an excess of supplies ‘sitting around’ on the site, construction site managers should instead order what is needed at the time, so that valuable materials are not left around waiting to be stolen for weeks at a time. Good planning and excellent communication between the team will be required so that projects are not delayed, but planning accordingly will help to reduce the chances of theft on a construction site. Drone surveillance As technology becomes more and more advanced, drone surveillance may soon be a security option that many construction sites could benefit from.Many construction firms in the UK are using drone services to provide aerial images, and are seeing huge cost savings by either purchasing and operating their own drones or by hiring out the work to a company equipped to provide imaging.As technology becomes more and more advanced, drone surveillance may soon be a security option With surveillance drones already handling tasks like mapping and surveying of construction sites, one day they may be able to patrol construction sites at night, equipped with motion sensors and infrared or night vision cameras; They could be automatically deployed from a charging station and fly along a pre-programmed route at regular intervals. One to keep an eye on for the near future! Construction site security to help protect your site If you are ready to tighten security on your own construction site, then your starting point will be to identify your main vulnerabilities and get in touch with a reputable security specialist.

AI in security: The crystal ball you’ve been waiting for
AI in security: The crystal ball you’ve been waiting for

One of the biggest trends in security and technology today is centered around solutions that take advantage of the wealth of connected security systems and devices powering the organisations all over the world. As the number of cloud-powered systems and sensors have massively grown in recent years, security leaders in the private and public sectors have started to look at ways to leverage the data from these devices to better the lives of employees, customers, and residents. But while the dream of creating a smarter, safer environment remains the top priority for organisations throughout the world especially as they continue to face the ramifications of the COVID-19 pandemic, a myriad of factors hold security leaders back from implementing more advanced technologies across their infrastructures. AI as a disruptor of physical security One of the main reasons being that the advent of these cloud based technologies indubitably generate massive amounts of data that hamper any practical use by security professionals and often times create cognitive overload and paralysis by analysis. A myriad of factors hold security leaders back from implementing more advanced technologies across their infrastructures Organisations face the challenge of trying to answer numerous questions using the big data generated by the various systems and technologies. How are they going to handle the influx of information that all these disparate systems generate? How can it be analysed to extract any useful information or insight? What IT security controls are put in place to safeguard the data? How can the data be effectively curated and funneled to the right people at the right time? How can we make our security footprint be more proactive rather than constantly reactive? The answer is artificial intelligence. AI is undoubtedly one of the bigger disrupters in the physical security industry and adoption is growing at a rapid rate. And it’s not just about video analytics. Rather, it is data AI, which is completely untapped by the security industry. Improving your competitive advantage Today, all divisions of an enterprise are trying to leverage AI and big data to improve their competitive advantage and bottom line, including accounting, sales and marketing, material sourcing, and research and development. We need to ensure that the physical security industry realises they can significantly benefit from better, faster, and more accurate intelligence from the now unstructured, bottomless silos of security data; only then will this result in positioning physical security from a primarily reactive business to a revolutionary new proactive environment. AI is undoubtedly one of the bigger disrupters in the physical security industry and adoption is growing at a rapid rate As an industry, we need to focus on reinventing how security personnel and safety resources are allocated in the public safety and corporate security industry. And it all has to start with intelligence derived from big data using AI. Security leaders in the physical security and law enforcement industry can combine multiple data sources with predictive and prescriptive analytics and artificial intelligence to inform and dynamically deploy personnel, assets, and technologies. This approach drives automation of their current manual processes to maximise the effectiveness and efficiency of their entire security operations. Intelligently predicting the future? Bottom line: AI can change up your security game by automatically deciphering information to predict the future using a wide range of sources and data that have been collected, whether past, present, and future. That’s right; you can look into the future. By grabbing a hold of this AI-powered crystal ball, decision-makers can perform long-term strategic planning and informed day-to-day operational decision making. And what’s more, AI powered platforms are software-based, often delivered using as-a-service business models that empower security personnel to go beyond traditional static business intelligence visualisation and reporting systems to transformative dynamic, predictive and prescriptive decision-making environments. Today’s platforms are also not your traditional, old school, expensive PSIMs; they are cost-effective, configurable to your needs and dare we say, easy to operate. Every security leader I have spoken with lately want to extend AI to their security programs. They don't always know precisely where AI will fit, but they understand the need to operationalise more of their security practices. The overall why is that we should all work collaboratively to help organisations across the globe leverage the tools available to transition away from a reactive stance and gain informed insight into the future where we are truly prepared for and one step ahead of what is coming down the road.